You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@magpie.apache.org by po...@apache.org on 2026/09/22 14:56:56 UTC

(magpie) branch principles/avoid-prompt-fatigue updated (0c1eb03c -> 216f76f5)

This is an automated email from the ASF dual-hosted git repository.

potiuk pushed a change to branch principles/avoid-prompt-fatigue
in repository https://gitbox.apache.org/repos/asf/magpie.git


 discard 0c1eb03c principles: add "Avoiding prompt fatigue" as §1, ahead of the security principle
    omit b1b9e956 fix(agent-isolation): list gh write subcommands in ask instead of a catch-all that prompted on every read
     add db56c022 fix(agent-isolation): list gh write subcommands in ask instead of a catch-all that prompted on every read (#1290)
     add 0e89fe46 feat(agent-isolation): touch overlay for ssh transport, and hardware-key setup as part of the secure setup (#1292)
     add ec64b811 feat(adapter/aider): Aider agent harness runtime guide (#1286)
     add 492b5826 chore: bump dev version to 0.2.0.dev202609191350 (#1293)
     add d8569a1c docs(sandbox): catalogue bind EPERM and Podman no-machine shapes in the doctor (#1294)
     add ee951157 feat(agent-isolation): touch overlay for git run from a terminal (#1295)
     add b69742a3 feat(adapter/gh-copilot): add GitHub Copilot CLI and Coding Agent skill runtime (#318) (#1287)
     add 17eb47f1 feat(release): reproducible source archives, reproducibility checks, and ASF automated signing (#1296)
     add c89d87b2 feat(container-gateway): run podman and docker from inside the sandbox through a policy proxy (#1298)
     add c02220e1 fix(pr-management-code-review): verify a review posted instead of retrying (#1300)
     add ea264ed1 fix(pr-management-code-review): guard against a bot-only green rollup (#1299)
     add 1001459e fix(agent-isolation): give every signing context its own touch watcher (#1301)
     add 41cedf53 fix(ci): trigger check-doc-sync on changes to the skill-evals tree (#1302)
     add 5a6e1509 chore: bump dev version to 0.2.0.dev202609202311 (#1303)
     add 0e7012ba fix(container-gateway): make the macOS path work end to end (#1304)
     add e9048938 fix(tools): request updatedAt so the stats events cache can go stale (#1305)
     add bf096478 fix(agent-isolation): keep the touch overlay's state out of /tmp (#1306)
     add 09b8930f chore: bump dev version to 0.2.0.dev202609210104 (#1307)
     add 47a76463 fix(sandbox): deny agent edits to the vetted-ops policy (#1308)
     add 85d16c9d fix(ci): exclude the vetted-ops policy from the sandbox-write-denied hooks (#1309)
     add 87be68b8 fix(vetted-ops): exclude the read dispatcher from the sandbox (#1310)
     add 5c75abd2 fix(sandbox): use Edit(path) for file denies, add the eval exclusion (#1311)
     add de5830a4 chore(spec-loop): sync specs to main and advance .last-sync (#1313)
     add 9f23f2d2 fix(agent-isolation): raise the touch overlay for key users other than git (#1314)
     add 0f4e0cf6 fix(skill-evals): contain fixture reads inside the eval tree (#1315)
     add 100952eb feat(tools/osv): query OSV.dev for vulnerability cross-references during security triage (#311) (#1297)
     add 4b206033 ci(prek): scope PR runs to the diff on ubuntu-slim, keep main whole-tree (#1317)
     add c36dedf1 fix(agent-isolation): disarm the touch overlay when a command never runs (#1316)
     add dd40ecd8 feat(agent-isolation): name the blocked command and its directory on the touch overlay (#1318)
     add 165a2cde chore: bump the dev version to 0.2.0.dev202609211315 (#1319)
     add 3f2cff94 fix(setup): stop the update skill reporting the dropped lychee domains as drift (#1321)
     add 43902b00 fix(setup): teach the update skill's drift check about the dispatcher hook flavour (#1322)
     add 7593508b fix(setup): recognise the agent-guard plugin as a complete install (#1323)
     add 6b0b9dbb fix(agent-isolation): close the macOS touch overlay when it loses the keyboard (#1325)
     add 5a5e1d67 feat(setup): reconciliation tracking for marketplace installs (#1324)
     add ddfef274 fix(agent-guard): resolve the git subcommand past global flags, not by a fixed argv slice (#1330)
     add 9456828b chore(deps): bump the python-deps group across 1 directory with 2 updates (#1328)
     add 37996fb4 chore(deps): bump astral-sh/setup-uv in the github-actions group (#1327)
     add c951c899 refactor(utilities): slim the authoring skills and teach optimize-skill to rewrite (#1331)
     add 216f76f5 principles: add "Avoiding prompt fatigue" as §1, ahead of the security principle

This update added new revisions after undoing existing revisions.
That is to say, some revisions that were in the old version of the
branch are not in the new version.  This situation occurs
when a user --force pushes a change and generates a repository
containing something like this:

 * -- * -- B -- O -- O -- O   (0c1eb03c)
            \
             N -- N -- N   refs/heads/principles/avoid-prompt-fatigue (216f76f5)

You should already have received notification emails for all of the O
revisions, and so the following emails describe only the N revisions
from the common base, B.

Any revisions marked "omit" are not gone; other references still
refer to them.  Any revisions marked "discard" are gone forever.

No new revisions were added by this update.

Summary of changes:
 .claude-plugin/marketplace.json                    |   24 +-
 .claude-plugin/plugin.json                         |    2 +-
 .claude/settings.json                              |    8 +-
 .codex-plugin/plugin.json                          |    2 +-
 .github/workflows/bump-dev-version.yml             |    2 +-
 .github/workflows/pre-commit.yml                   |  131 +-
 .github/workflows/sandbox-lint.yml                 |    2 +-
 .github/workflows/skill-and-tool-validator.yml     |    2 +-
 .github/workflows/skill-token-count.yml            |    2 +-
 .github/workflows/tests.yml                        |    2 +-
 .github/workflows/zizmor.yml                       |    2 +-
 .lychee.toml                                       |    9 +
 .pre-commit-config.yaml                            |  117 +-
 .typos.toml                                        |    7 +-
 AGENTS.md                                          |   38 +-
 CONTRIBUTING.md                                    |   26 +-
 apm.yml                                            |    2 +-
 assets/quickstart/wizard/release-management.svg    |    2 +-
 docs/adapters/README.md                            |   14 +-
 docs/adapters/aider.md                             |  233 ++++
 docs/adapters/codex.md                             |    2 +-
 docs/adapters/copilot.md                           |  239 ++++
 docs/adapters/registry.md                          |    4 +-
 docs/designs/2026-09-20-reproducible-releases.md   |  240 ++++
 ...26-09-21-marketplace-reconciliation-tracking.md |  572 +++++++++
 docs/designs/README.md                             |    2 +
 docs/labels-and-capabilities.md                    |    7 +
 docs/mode-economics.md                             |  184 +--
 docs/quick-start/prerequisites.md                  |   10 +-
 docs/release-management/README.md                  |    2 +-
 docs/release-management/atr-release-runbook.md     |   38 +-
 docs/release-management/manual-release-process.md  |   42 +
 docs/release-management/process.md                 |   95 +-
 docs/release-management/reproducibility.md         |  270 ++++
 docs/release-management/spec.md                    |  105 +-
 docs/release-management/svn-release-runbook.md     |   29 +-
 docs/rfcs/RFC-AI-0002.md                           |   19 +-
 docs/rfcs/RFC-AI-0003.md                           |    6 +
 docs/rfcs/RFC-AI-0004.md                           |    1 +
 docs/setup/agentic-overrides.md                    |   22 +
 docs/setup/marketplace.md                          |    4 +-
 docs/setup/sandbox-troubleshooting.md              |  488 ++++---
 docs/setup/secure-agent-setup.md                   |  623 ++++++++-
 docs/source-release-contents.md                    |    6 +-
 docs/vendor-neutrality.md                          |   22 +-
 gemini-extension.json                              |    2 +-
 organizations/ASF/organization.md                  |   11 +
 organizations/independent/organization.md          |    1 +
 plugin.json                                        |    2 +-
 .../magpie-agent-guard/.claude-plugin/plugin.json  |    2 +-
 .../.claude-plugin/plugin.json                     |    2 +-
 .../skills/activity-sweep/SKILL.md                 |  162 +--
 .../skills/committer-onboarding/SKILL.md           |  162 +--
 .../skills/contributor-to-committer/SKILL.md       |  162 +--
 .../skills/nomination/SKILL.md                     |  162 +--
 .../skills/onboarding-concierge/SKILL.md           |  162 +--
 .../skills/sentiment/SKILL.md                      |  162 +--
 plugins/magpie-issue/.claude-plugin/plugin.json    |    2 +-
 plugins/magpie-issue/skills/backlog-stats/SKILL.md |  166 +--
 plugins/magpie-issue/skills/deduplicate/SKILL.md   |  162 +--
 plugins/magpie-issue/skills/fix-workflow/SKILL.md  |  166 +--
 .../magpie-issue/skills/reassess-stats/SKILL.md    |  166 +--
 plugins/magpie-issue/skills/reassess/SKILL.md      |  162 +--
 plugins/magpie-issue/skills/reproducer/SKILL.md    |  166 +--
 plugins/magpie-issue/skills/stale-sweep/SKILL.md   |  162 +--
 plugins/magpie-issue/skills/triage/SKILL.md        |  162 +--
 .../magpie-mentoring/.claude-plugin/plugin.json    |    2 +-
 .../skills/good-first-issue-author/SKILL.md        |  166 +--
 .../skills/good-first-issue-sweep/SKILL.md         |  162 +--
 .../skills/newcomer-issue-explainer/SKILL.md       |  162 +--
 plugins/magpie-mentoring/skills/welcome/SKILL.md   |  166 +--
 plugins/magpie-pairing/.claude-plugin/plugin.json  |    2 +-
 .../skills/multi-agent-review/SKILL.md             |  162 +--
 plugins/magpie-pairing/skills/self-review/SKILL.md |  162 +--
 .../.claude-plugin/plugin.json                     |    2 +-
 .../skills/code-review/SKILL.md                    |  182 +--
 .../skills/code-review/posting.md                  |   32 +
 .../skills/code-review/prerequisites.md            |   43 +-
 .../magpie-pr-management/skills/mentor/SKILL.md    |  166 +--
 .../skills/pre-first-pr-check/SKILL.md             |  162 +--
 .../skills/quick-merge/SKILL.md                    |  162 +--
 .../skills/reviewer-routing/SKILL.md               |  162 +--
 .../skills/stale-sweep/SKILL.md                    |  162 +--
 plugins/magpie-pr-management/skills/stats/SKILL.md |  166 +--
 .../magpie-pr-management/skills/triage/SKILL.md    |  162 +--
 .../.claude-plugin/plugin.json                     |    2 +-
 .../skills/announce-draft/SKILL.md                 |  165 +--
 .../skills/archive-sweep/SKILL.md                  |  162 +--
 .../skills/audit-report/SKILL.md                   |  162 +--
 .../skills/keys-sync/SKILL.md                      |  162 +--
 .../skills/prepare/SKILL.md                        |  475 ++++---
 .../skills/promote/SKILL.md                        |  225 ++--
 .../skills/rc-cut/SKILL.md                         |  548 +++++---
 .../skills/verify-rc/SKILL.md                      |  427 ++++---
 .../skills/vote-draft/SKILL.md                     |  251 ++--
 .../skills/vote-tally/SKILL.md                     |  162 +--
 .../magpie-repo-health/.claude-plugin/plugin.json  |    2 +-
 .../skills/audit-finding-fix/SKILL.md              |  162 +--
 .../skills/ci-runner-audit/SKILL.md                |  162 +--
 .../skills/dependency-audit/SKILL.md               |  162 +--
 .../skills/dependency-license-audit/SKILL.md       |  162 +--
 .../skills/flaky-test-triage/SKILL.md              |  162 +--
 .../skills/license-compliance-audit/SKILL.md       |  162 +--
 .../skills/workflow-security-audit/SKILL.md        |  162 +--
 plugins/magpie-security/.claude-plugin/plugin.json |    2 +-
 .../magpie-security/skills/cve-allocate/SKILL.md   |  162 +--
 .../skills/issue-deduplicate/SKILL.md              |  162 +--
 plugins/magpie-security/skills/issue-fix/SKILL.md  |  162 +--
 .../skills/issue-import-from-md/SKILL.md           |  162 +--
 .../skills/issue-import-from-pr/SKILL.md           |  162 +--
 .../skills/issue-import-from-scan/SKILL.md         |  166 +--
 .../skills/issue-import-via-forwarder/SKILL.md     |  162 +--
 .../magpie-security/skills/issue-import/SKILL.md   |  162 +--
 .../skills/issue-invalidate/SKILL.md               |  162 +--
 plugins/magpie-security/skills/issue-sync/SKILL.md |  166 +--
 .../magpie-security/skills/issue-triage/SKILL.md   |  162 +--
 .../magpie-security/skills/model-prepare/SKILL.md  |  166 +--
 .../magpie-security/skills/model-update/SKILL.md   |  162 +--
 .../magpie-security/skills/model-verify/SKILL.md   |  162 +--
 .../skills/tracker-stats-dashboard/SKILL.md        |  166 +--
 plugins/magpie-setup/.claude-plugin/plugin.json    |    2 +-
 .../skills/isolated-setup-doctor/SKILL.md          |  218 +++-
 .../skills/isolated-setup-install/SKILL.md         |  245 +++-
 .../skills/isolated-setup-update/SKILL.md          |  132 +-
 .../skills/isolated-setup-verify/SKILL.md          |  178 ++-
 .../magpie-setup/skills/override-upstream/SKILL.md |    1 +
 plugins/magpie-setup/skills/privacy-llm/SKILL.md   |    1 +
 plugins/magpie-setup/skills/setup/SKILL.md         |   17 +-
 plugins/magpie-setup/skills/setup/adopt.md         |   78 +-
 plugins/magpie-setup/skills/setup/config.md        |  127 +-
 plugins/magpie-setup/skills/setup/install.md       |   79 +-
 plugins/magpie-setup/skills/setup/locks.md         |  172 +++
 plugins/magpie-setup/skills/setup/reconcile.md     |  306 +++++
 plugins/magpie-setup/skills/setup/uninstall.md     |   15 +-
 plugins/magpie-setup/skills/setup/upgrade.md       |  143 ++-
 plugins/magpie-setup/skills/setup/verify.md        |  163 ++-
 .../skills/shared-config-sync/SKILL.md             |    1 +
 plugins/magpie-setup/skills/status/SKILL.md        |    1 +
 plugins/magpie-setup/skills/upstream-fix/SKILL.md  |    1 +
 .../magpie-utilities/.claude-plugin/plugin.json    |    2 +-
 .../magpie-utilities/skills/list-skills/SKILL.md   |  162 +--
 .../skills/optimize-skill/SKILL.md                 |  532 +++-----
 .../skills/optimize-skill/rewrite.md               |   87 ++
 .../skills/report-framework-issue/SKILL.md         |  162 +--
 .../skills/skill-reconciler/SKILL.md               |  162 +--
 .../magpie-utilities/skills/write-skill/SKILL.md   |  639 ++-------
 .../magpie-utilities/skills/write-skill/anatomy.md |   52 +
 .../skills/write-skill/conventions.md              |   82 ++
 .../skills/write-skill/provenance.md               |   41 +
 .../magpie-vetted-ops/.claude-plugin/plugin.json   |    2 +-
 projects/_template/README.md                       |    2 +-
 projects/_template/project.md                      |   15 +
 projects/_template/release-build.md                |  177 ++-
 projects/_template/release-management-config.md    |   44 +
 projects/_template/workflows/release-candidate.yml |  184 +++
 projects/magpie/release-build.md                   |   84 +-
 projects/magpie/release-management-config.md       |    3 +
 pyproject.toml                                     |    5 +-
 tools/agent-guard/src/agent_guard/__init__.py      |   71 +-
 .../src/agent_guard/guards.d/no_verify_commit.py   |    2 +-
 tools/agent-guard/tests/test_guards.py             |   65 +
 tools/agent-isolation/README.md                    |    5 +-
 tools/agent-isolation/container-gateway-hook.sh    |  115 ++
 .../gpg-touch-overlay-window-macos.py              |  101 +-
 tools/agent-isolation/gpg-touch-overlay-window.py  |   76 +-
 tools/agent-isolation/gpg-touch-overlay.sh         |  637 ++++++++-
 tools/agent-isolation/sandbox-error-hint.sh        |    9 +-
 .../tests/test_container_gateway_hook.py           |  195 +++
 .../tests/test_gpg_touch_overlay.py                |  950 +++++++++++++-
 .../tests/test_sandbox_error_hint.py               |   41 +
 tools/container-gateway/.gitignore                 |    2 +
 tools/container-gateway/README.md                  |  152 +++
 tools/container-gateway/pyproject.toml             |   62 +
 .../src/container_gateway/__init__.py              |   19 +
 .../src/container_gateway/__main__.py              |  291 +++++
 .../src/container_gateway/backends.py              |  107 ++
 .../src/container_gateway/daemon.py                |  654 ++++++++++
 .../src/container_gateway/decisions.py             |  581 +++++++++
 .../src/container_gateway/http.py                  |  393 ++++++
 .../src/container_gateway/labels.py                |   77 ++
 .../src/container_gateway/policy.py                |  939 ++++++++++++++
 .../src/container_gateway/policy_shape.py          |  713 +++++++++++
 .../src/container_gateway/relay.py                 |  611 +++++++++
 .../src/container_gateway/routes.py                |  285 +++++
 .../tests/__init__.py                              |    0
 tools/container-gateway/tests/fakebackend.py       |  244 ++++
 tools/container-gateway/tests/test_backends.py     |  112 ++
 tools/container-gateway/tests/test_daemon.py       | 1352 ++++++++++++++++++++
 tools/container-gateway/tests/test_http.py         |  476 +++++++
 tools/container-gateway/tests/test_imports.py      |   50 +
 tools/container-gateway/tests/test_integration.py  |  221 ++++
 tools/container-gateway/tests/test_labels.py       |   87 ++
 tools/container-gateway/tests/test_package.py      |   25 +
 tools/container-gateway/tests/test_policy_build.py |  262 ++++
 .../container-gateway/tests/test_policy_create.py  |  917 +++++++++++++
 .../container-gateway/tests/test_policy_images.py  |   73 ++
 .../container-gateway/tests/test_policy_labels.py  |  329 +++++
 tools/container-gateway/tests/test_relay.py        |  743 +++++++++++
 tools/container-gateway/tests/test_routes.py       |  129 ++
 tools/container-gateway/tool.md                    |  165 +++
 tools/dev/README.md                                |    6 +-
 tools/dev/blocks/asf-detection.md                  |    8 +
 tools/dev/blocks/both-stores-collision.md          |   14 +
 tools/dev/blocks/main-checkout-precheck.md         |    6 +
 tools/dev/blocks/sandbox-allowlist-helper.md       |   14 +
 tools/dev/blocks/worktree-enumeration.md           |   19 +
 tools/dev/check-duplication.py                     |  399 ++++++
 tools/dev/check-shared-blocks.py                   |  453 +++++++
 tools/dev/check-skill-preflight.py                 |  179 ---
 tools/dev/preflight-block.md                       |  162 +--
 tools/dev/skill-surface-hash.py                    |  270 ++++
 tools/dev/tests/test_check_duplication.py          |  346 +++++
 tools/dev/tests/test_check_shared_blocks.py        |  468 +++++++
 tools/dev/tests/test_skill_surface_hash.py         |  315 +++++
 .../egress-gateway/src/egress_gateway/allowlist.py |    3 +
 tools/egress-gateway/tests/test_allowlist.py       |    1 +
 tools/egress-gateway/tool.md                       |    1 +
 tools/osv/README.md                                |   38 +
 tools/osv/tool.md                                  |  168 +++
 tools/reproducible-archive/README.md               |  187 +++
 tools/reproducible-archive/pyproject.toml          |   89 ++
 .../src/reproducible_archive/__init__.py           |  841 ++++++++++++
 .../tests/test_reproducible_archive.py             |  468 +++++++
 tools/sandbox-lint/README.md                       |   30 +-
 tools/sandbox-lint/expected.json                   |    8 +-
 tools/sandbox-lint/src/sandbox_lint/__init__.py    |   83 +-
 .../tests/test_doc_domain_consistency.py           |   75 ++
 tools/sandbox-lint/tests/test_validator.py         |  141 ++
 .../fetch_issues.py                                |    6 +-
 .../tests/test_fetch_fields.py                     |   52 +
 tools/setup-preflight/README.md                    |  151 +++
 tools/setup-preflight/pyproject.toml               |   91 ++
 .../src/setup_preflight}/__init__.py               |    0
 .../src/setup_preflight/__main__.py                |   27 +
 tools/setup-preflight/src/setup_preflight/cli.py   |  164 +++
 tools/setup-preflight/src/setup_preflight/core.py  |  379 ++++++
 .../src/setup_preflight/lockfile.py                |  142 ++
 .../src/setup_preflight/sections.py                |   85 ++
 .../src/setup_preflight/sections/step-10.md        |   17 +
 .../src/setup_preflight/sections/step-2.md         |   14 +
 .../src/setup_preflight/sections/step-3.md         |   33 +
 .../src/setup_preflight/sections/step-4.md         |   49 +
 .../src/setup_preflight/sections/step-5.md         |   18 +
 .../src/setup_preflight/sections/step-7.md         |   18 +
 .../src/setup_preflight/sections/step-8.md         |   14 +
 .../src/setup_preflight/sections/step-9.md         |   34 +
 .../setup-preflight/src/setup_preflight/version.py |   88 ++
 .../tests/__init__.py                              |    0
 tools/setup-preflight/tests/conftest.py            |   41 +
 tools/setup-preflight/tests/test_cli.py            |  140 ++
 tools/setup-preflight/tests/test_core.py           |  280 ++++
 tools/setup-preflight/tests/test_sections.py       |   67 +
 tools/setup-preflight/tests/test_version.py        |   57 +
 .../src/skill_and_tool_validator/__init__.py       |   44 +-
 .../tests/test_validator.py                        |   66 +-
 tools/skill-evals/README.md                        |  117 +-
 .../evals/pr-management-code-review/README.md      |    4 +-
 .../fixtures/case-6-bot-only-rollup/expected.json  |    4 +
 .../fixtures/case-6-bot-only-rollup/report.md      |   19 +
 .../review-disposition/fixtures/system-prompt.md   |    3 +-
 .../evals/preflight-reconciliation/README.md       |   85 ++
 .../fixtures/case-1-in-sync/expected.json          |    1 +
 .../fixtures/case-1-in-sync/report.md              |   12 +
 .../fixtures/case-2-config-moved/expected.json     |    1 +
 .../fixtures/case-2-config-moved/report.md         |   40 +
 .../fixtures/case-3-anchor-moved/expected.json     |    1 +
 .../fixtures/case-3-anchor-moved/report.md         |   29 +
 .../fixtures/case-4-no-stamp/expected.json         |    1 +
 .../fixtures/case-4-no-stamp/report.md             |   25 +
 .../fixtures/case-5-declined/expected.json         |    1 +
 .../fixtures/case-5-declined/report.md             |   12 +
 .../case-6-skill-absent-from-stamp/expected.json   |    1 +
 .../case-6-skill-absent-from-stamp/report.md       |   12 +
 .../case-7-no-config-surface/expected.json         |    1 +
 .../fixtures/case-7-no-config-surface/report.md    |   12 +
 .../step-reconciliation/fixtures/output-spec.md    |   33 +
 .../step-reconciliation}/fixtures/step-config.json |    0
 .../fixtures/user-prompt-template.md               |    8 +
 tools/skill-evals/evals/release-prepare/README.md  |   28 +-
 .../case-5-automated-signing-non-asf/expected.json |    6 +
 .../case-5-automated-signing-non-asf/report.md     |   17 +
 .../case-6-automated-signing-asf/expected.json     |    7 +
 .../case-6-automated-signing-asf/report.md         |   24 +
 .../step-0-preflight/fixtures/output-spec.md       |   11 +-
 .../step-2-prep/fixtures/assertions.json           |   24 +
 .../fixtures/case-1-clean-prep/expected.json       |    1 +
 .../fixtures/case-1-clean-prep/report.md           |    4 +
 .../fixtures/case-2-category-x-hit/report.md       |    4 +
 .../case-3-notice-removal-unjustified/report.md    |    4 +
 .../expected.json                                  |   15 +
 .../case-4-first-release-archive-review/report.md  |   37 +
 .../step-2-prep/fixtures/output-spec.md            |    9 +
 tools/skill-evals/evals/release-promote/README.md  |   16 +-
 .../step-2-emit-commands/fixtures/assertions.json  |   19 +
 .../case-5-convenience-artefacts/expected.json     |   15 +
 .../case-5-convenience-artefacts/report.md         |   46 +
 .../step-2-emit-commands/fixtures/output-spec.md   |   11 +-
 tools/skill-evals/evals/release-rc-cut/README.md   |   56 +-
 .../fixtures/case-1-clean-pass/expected.json       |    3 +-
 .../fixtures/case-1-clean-pass/report.md           |    2 +
 .../case-2-prep-pr-not-merged/expected.json        |    3 +-
 .../fixtures/case-2-prep-pr-not-merged/report.md   |    2 +
 .../fixtures/case-3-rc-tag-exists/expected.json    |    3 +-
 .../fixtures/case-3-rc-tag-exists/report.md        |    2 +
 .../case-4-archive-unreviewed/expected.json        |    6 +
 .../fixtures/case-4-archive-unreviewed/report.md   |   29 +
 .../step-0-preflight/fixtures/output-spec.md       |    9 +-
 .../step-2-tag-build-sign/fixtures/assertions.json |   24 +
 .../fixtures/case-1-svnpubsub-sha512/expected.json |    4 +-
 .../fixtures/case-1-svnpubsub-sha512/report.md     |    4 +
 .../case-2-sha512-and-sha256/expected.json         |    4 +-
 .../fixtures/case-2-sha512-and-sha256/report.md    |    4 +
 .../case-3-prohibited-digest-refused/expected.json |    4 +-
 .../case-3-prohibited-digest-refused/report.md     |    4 +
 .../expected.json                                  |    3 +-
 .../case-4-git-archive-reproducible/report.md      |   20 +
 .../step-2-tag-build-sign/fixtures/output-spec.md  |    8 +-
 .../fixtures/assertions.json                       |   57 +
 .../fixtures/case-1-source-only/expected.json      |   13 +
 .../fixtures/case-1-source-only/report.md          |   19 +
 .../expected.json                                  |   14 +
 .../case-2-source-and-binaries-ci-signed/report.md |   23 +
 .../fixtures/case-3-checks-off/expected.json       |    9 +
 .../fixtures/case-3-checks-off/report.md           |   14 +
 .../fixtures/output-spec.md                        |   36 +
 .../fixtures/step-config.json                      |    4 +
 .../skill-evals/evals/release-verify-rc/README.md  |   18 +-
 .../fixtures/case-1-identical-pass/expected.json   |   23 +
 .../fixtures/case-1-identical-pass/report.md       |   29 +
 .../fixtures/case-2-differs-fail/expected.json     |   25 +
 .../fixtures/case-2-differs-fail/report.md         |   26 +
 .../case-3-content-identical-warn/expected.json    |   20 +
 .../case-3-content-identical-warn/report.md        |   26 +
 .../expected.json                                  |   19 +
 .../report.md                                      |   26 +
 .../expected.json                                  |   19 +
 .../case-5-convenience-artefact-differs/report.md  |   29 +
 .../fixtures/grading-schema.json                   |    0
 .../step-9-reproducibility/fixtures/output-spec.md |   57 +
 .../fixtures/step-config.json                      |    4 +
 .../skill-evals/evals/release-vote-draft/README.md |    2 +-
 .../step-2-vote-draft/fixtures/assertions.json     |   51 +
 .../fixtures/case-1-standard-vote/expected.json    |   11 +-
 .../fixtures/case-1-standard-vote/report.md        |    7 +
 .../fixtures/case-2-expedited-vote/expected.json   |   10 +-
 .../fixtures/case-2-expedited-vote/report.md       |    7 +
 .../case-3-skip-verify-logged/expected.json        |    9 +-
 .../fixtures/case-3-skip-verify-logged/report.md   |    6 +
 .../step-2-vote-draft/fixtures/output-spec.md      |    7 +
 .../evals/setup-isolated-setup-doctor/README.md    |   30 +-
 .../expected.json                                  |    0
 .../fixtures/case-10-gateway-pass/report.md        |    9 +
 .../case-11-gateway-not-running/expected.json      |    1 +
 .../fixtures/case-11-gateway-not-running/report.md |    9 +
 .../case-12-gateway-socket-denied/expected.json    |    1 +
 .../case-12-gateway-socket-denied/report.md        |    9 +
 .../expected.json                                  |    1 +
 .../case-13-gateway-no-podman-backend/report.md    |    9 +
 .../expected.json                                  |    1 +
 .../case-14-scratch-shared-session-root/report.md  |   12 +
 .../expected.json                                  |    1 +
 .../report.md                                      |   12 +
 .../interpret-probes/fixtures/output-spec.md       |    6 +-
 .../evals/setup-isolated-setup-install/README.md   |    7 +-
 .../fixtures/case-1-no-key}/case-meta.json         |    0
 .../fixtures/case-1-no-key/expected.json           |    1 +
 .../fixtures/case-1-no-key/report.md               |   15 +
 .../fixtures/case-2-slots-off}/case-meta.json      |    0
 .../fixtures/case-2-slots-off/expected.json        |    1 +
 .../fixtures/case-2-slots-off/report.md            |   33 +
 .../fixtures/case-3-injection/expected.json        |    1 +
 .../fixtures/case-3-injection/report.md            |   31 +
 .../step-hardware-key/fixtures/output-spec.md      |   25 +
 .../step-hardware-key/fixtures/step-config.json    |    4 +
 .../fixtures/user-prompt-template.md               |    8 +
 .../evals/setup-isolated-setup-verify/README.md    |    2 +-
 .../case-7-signing-key-unreadable/report.md        |    2 +-
 .../step-1-classify/fixtures/step-config.json      |    2 +-
 tools/skill-evals/evals/setup/README.md            |   19 +-
 .../setup/preflight-floor/fixtures/assertions.json |    6 +
 .../fixtures/case-1-at-floor/expected.json         |    2 +-
 .../fixtures/case-1-at-floor/report.md             |    7 +-
 .../case-8-unknown-plugin-list/expected.json       |    1 +
 .../fixtures/case-8-unknown-plugin-list/report.md  |   19 +
 .../case-1-migrate-and-scope/expected.json         |    1 +
 .../fixtures/case-1-migrate-and-scope/report.md    |   25 +
 .../setup/step-adopt-stamp/fixtures/output-spec.md |   33 +
 .../step-adopt-stamp/fixtures/step-config.json     |    4 +
 .../fixtures/user-prompt-template.md               |    8 +
 .../fixtures/case-1-adopted-project/expected.json  |    1 +
 .../fixtures/case-1-adopted-project/report.md      |   22 +
 .../case-2-unadopted-project/expected.json         |    1 +
 .../fixtures/case-2-unadopted-project/report.md    |   20 +
 .../case-3-nothing-configured-yet/expected.json    |    1 +
 .../case-3-nothing-configured-yet/report.md        |   16 +
 .../case-4-adopted-untouched-skill/expected.json   |    1 +
 .../case-4-adopted-untouched-skill/report.md       |   19 +
 .../step-config-stamp/fixtures/output-spec.md      |   49 +
 .../step-config-stamp/fixtures/step-config.json    |    4 +
 .../fixtures/user-prompt-template.md               |    8 +
 .../fixtures/case-1-clean-sweep/expected.json      |    1 +
 .../fixtures/case-1-clean-sweep/report.md          |   25 +
 .../fixtures/case-2-stale-anchor/expected.json     |   12 +
 .../fixtures/case-2-stale-anchor/report.md         |   25 +
 .../fixtures/case-3-sandboxed-run/expected.json    |    1 +
 .../fixtures/case-3-sandboxed-run/report.md        |   23 +
 .../step-reconcile/fixtures/grading-schema.json    |    3 +
 .../setup/step-reconcile/fixtures/output-spec.md   |   39 +
 .../setup/step-reconcile/fixtures/step-config.json |    4 +
 .../fixtures/user-prompt-template.md               |    8 +
 .../fixtures/case-1-mixed-checks/expected.json     |    1 +
 .../fixtures/case-1-mixed-checks/report.md         |   45 +
 .../fixtures/grading-schema.json                   |    3 +
 .../step-upgrade-stamp/fixtures/output-spec.md     |   37 +
 .../step-upgrade-stamp/fixtures/step-config.json   |    4 +
 .../fixtures/user-prompt-template.md               |    8 +
 .../fixtures/case-1-dev-to-dev-delta/expected.json |   10 +
 .../fixtures/case-1-dev-to-dev-delta/report.md     |   52 +
 .../fixtures/case-2-unreadable-clone/expected.json |    4 +
 .../fixtures/case-2-unreadable-clone/report.md     |   52 +
 .../setup/step-verify/fixtures/output-spec.md      |   32 +
 .../setup/step-verify/fixtures/step-config.json    |    4 +
 .../step-verify/fixtures/user-prompt-template.md   |    8 +
 tools/skill-evals/magpie-run-evals.sh              |  165 +++
 tools/skill-evals/src/skill_evals/runner.py        |   74 +-
 tools/skill-evals/tests/test_run_evals_wrapper.py  |   95 ++
 tools/skill-evals/tests/test_runner.py             |  130 ++
 tools/spec-loop/.last-sync                         |    2 +-
 tools/spec-loop/specs/README.md                    |    4 +-
 tools/spec-loop/specs/adoption-and-setup.md        |  163 ++-
 tools/spec-loop/specs/agent-isolation-sandbox.md   |  113 +-
 tools/spec-loop/specs/codex-runtime.md             |    2 +-
 tools/spec-loop/specs/container-gateway.md         |  479 +++++++
 tools/spec-loop/specs/copilot-runtime.md           |  150 +++
 tools/spec-loop/specs/marketplace-distribution.md  |   22 +
 tools/spec-loop/specs/overview.md                  |    2 +
 tools/spec-loop/specs/pr-management-family.md      |   22 +
 .../specs/release-management-lifecycle.md          |   50 +-
 tools/spec-loop/specs/sandbox-diagnostics.md       |   19 +-
 tools/spec-loop/specs/security-reporting.md        |    5 +-
 .../src/vendor_neutrality_score/__init__.py        |    4 +
 tools/vetted-ops/README.md                         |   29 +-
 uv.lock                                            |  108 +-
 443 files changed, 32056 insertions(+), 10216 deletions(-)
 create mode 100644 docs/adapters/aider.md
 create mode 100644 docs/adapters/copilot.md
 create mode 100644 docs/designs/2026-09-20-reproducible-releases.md
 create mode 100644 docs/designs/2026-09-21-marketplace-reconciliation-tracking.md
 create mode 100644 docs/release-management/reproducibility.md
 create mode 100644 plugins/magpie-setup/skills/setup/reconcile.md
 create mode 100644 plugins/magpie-utilities/skills/optimize-skill/rewrite.md
 create mode 100644 plugins/magpie-utilities/skills/write-skill/anatomy.md
 create mode 100644 plugins/magpie-utilities/skills/write-skill/conventions.md
 create mode 100644 plugins/magpie-utilities/skills/write-skill/provenance.md
 create mode 100644 projects/_template/workflows/release-candidate.yml
 create mode 100755 tools/agent-isolation/container-gateway-hook.sh
 create mode 100644 tools/agent-isolation/tests/test_container_gateway_hook.py
 create mode 100644 tools/container-gateway/.gitignore
 create mode 100644 tools/container-gateway/README.md
 create mode 100644 tools/container-gateway/pyproject.toml
 create mode 100644 tools/container-gateway/src/container_gateway/__init__.py
 create mode 100644 tools/container-gateway/src/container_gateway/__main__.py
 create mode 100644 tools/container-gateway/src/container_gateway/backends.py
 create mode 100644 tools/container-gateway/src/container_gateway/daemon.py
 create mode 100644 tools/container-gateway/src/container_gateway/decisions.py
 create mode 100644 tools/container-gateway/src/container_gateway/http.py
 create mode 100644 tools/container-gateway/src/container_gateway/labels.py
 create mode 100644 tools/container-gateway/src/container_gateway/policy.py
 create mode 100644 tools/container-gateway/src/container_gateway/policy_shape.py
 create mode 100644 tools/container-gateway/src/container_gateway/relay.py
 create mode 100644 tools/container-gateway/src/container_gateway/routes.py
 copy tools/{agent-isolation => container-gateway}/tests/__init__.py (100%)
 create mode 100644 tools/container-gateway/tests/fakebackend.py
 create mode 100644 tools/container-gateway/tests/test_backends.py
 create mode 100644 tools/container-gateway/tests/test_daemon.py
 create mode 100644 tools/container-gateway/tests/test_http.py
 create mode 100644 tools/container-gateway/tests/test_imports.py
 create mode 100644 tools/container-gateway/tests/test_integration.py
 create mode 100644 tools/container-gateway/tests/test_labels.py
 create mode 100644 tools/container-gateway/tests/test_package.py
 create mode 100644 tools/container-gateway/tests/test_policy_build.py
 create mode 100644 tools/container-gateway/tests/test_policy_create.py
 create mode 100644 tools/container-gateway/tests/test_policy_images.py
 create mode 100644 tools/container-gateway/tests/test_policy_labels.py
 create mode 100644 tools/container-gateway/tests/test_relay.py
 create mode 100644 tools/container-gateway/tests/test_routes.py
 create mode 100644 tools/container-gateway/tool.md
 create mode 100644 tools/dev/blocks/asf-detection.md
 create mode 100644 tools/dev/blocks/both-stores-collision.md
 create mode 100644 tools/dev/blocks/main-checkout-precheck.md
 create mode 100644 tools/dev/blocks/sandbox-allowlist-helper.md
 create mode 100644 tools/dev/blocks/worktree-enumeration.md
 create mode 100644 tools/dev/check-duplication.py
 create mode 100644 tools/dev/check-shared-blocks.py
 delete mode 100755 tools/dev/check-skill-preflight.py
 create mode 100644 tools/dev/skill-surface-hash.py
 create mode 100644 tools/dev/tests/test_check_duplication.py
 create mode 100644 tools/dev/tests/test_check_shared_blocks.py
 create mode 100644 tools/dev/tests/test_skill_surface_hash.py
 create mode 100644 tools/osv/README.md
 create mode 100644 tools/osv/tool.md
 create mode 100644 tools/reproducible-archive/README.md
 create mode 100644 tools/reproducible-archive/pyproject.toml
 create mode 100644 tools/reproducible-archive/src/reproducible_archive/__init__.py
 create mode 100644 tools/reproducible-archive/tests/test_reproducible_archive.py
 create mode 100644 tools/sandbox-lint/tests/test_doc_domain_consistency.py
 create mode 100644 tools/security-tracker-stats-dashboard/tests/test_fetch_fields.py
 create mode 100644 tools/setup-preflight/README.md
 create mode 100644 tools/setup-preflight/pyproject.toml
 copy tools/{cve-tool-vulnogram/generate-cve-json/tests => setup-preflight/src/setup_preflight}/__init__.py (100%)
 create mode 100644 tools/setup-preflight/src/setup_preflight/__main__.py
 create mode 100644 tools/setup-preflight/src/setup_preflight/cli.py
 create mode 100644 tools/setup-preflight/src/setup_preflight/core.py
 create mode 100644 tools/setup-preflight/src/setup_preflight/lockfile.py
 create mode 100644 tools/setup-preflight/src/setup_preflight/sections.py
 create mode 100644 tools/setup-preflight/src/setup_preflight/sections/step-10.md
 create mode 100644 tools/setup-preflight/src/setup_preflight/sections/step-2.md
 create mode 100644 tools/setup-preflight/src/setup_preflight/sections/step-3.md
 create mode 100644 tools/setup-preflight/src/setup_preflight/sections/step-4.md
 create mode 100644 tools/setup-preflight/src/setup_preflight/sections/step-5.md
 create mode 100644 tools/setup-preflight/src/setup_preflight/sections/step-7.md
 create mode 100644 tools/setup-preflight/src/setup_preflight/sections/step-8.md
 create mode 100644 tools/setup-preflight/src/setup_preflight/sections/step-9.md
 create mode 100644 tools/setup-preflight/src/setup_preflight/version.py
 copy tools/{cve-tool-vulnogram/generate-cve-json => setup-preflight}/tests/__init__.py (100%)
 create mode 100644 tools/setup-preflight/tests/conftest.py
 create mode 100644 tools/setup-preflight/tests/test_cli.py
 create mode 100644 tools/setup-preflight/tests/test_core.py
 create mode 100644 tools/setup-preflight/tests/test_sections.py
 create mode 100644 tools/setup-preflight/tests/test_version.py
 create mode 100644 tools/skill-evals/evals/pr-management-code-review/review-disposition/fixtures/case-6-bot-only-rollup/expected.json
 create mode 100644 tools/skill-evals/evals/pr-management-code-review/review-disposition/fixtures/case-6-bot-only-rollup/report.md
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/README.md
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/case-1-in-sync/expected.json
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/case-1-in-sync/report.md
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/case-2-config-moved/expected.json
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/case-2-config-moved/report.md
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/case-3-anchor-moved/expected.json
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/case-3-anchor-moved/report.md
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/case-4-no-stamp/expected.json
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/case-4-no-stamp/report.md
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/case-5-declined/expected.json
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/case-5-declined/report.md
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/case-6-skill-absent-from-stamp/expected.json
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/case-6-skill-absent-from-stamp/report.md
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/case-7-no-config-surface/expected.json
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/case-7-no-config-surface/report.md
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/output-spec.md
 copy tools/skill-evals/evals/{setup/preflight-floor => preflight-reconciliation/step-reconciliation}/fixtures/step-config.json (100%)
 create mode 100644 tools/skill-evals/evals/preflight-reconciliation/step-reconciliation/fixtures/user-prompt-template.md
 create mode 100644 tools/skill-evals/evals/release-prepare/step-0-preflight/fixtures/case-5-automated-signing-non-asf/expected.json
 create mode 100644 tools/skill-evals/evals/release-prepare/step-0-preflight/fixtures/case-5-automated-signing-non-asf/report.md
 create mode 100644 tools/skill-evals/evals/release-prepare/step-0-preflight/fixtures/case-6-automated-signing-asf/expected.json
 create mode 100644 tools/skill-evals/evals/release-prepare/step-0-preflight/fixtures/case-6-automated-signing-asf/report.md
 create mode 100644 tools/skill-evals/evals/release-prepare/step-2-prep/fixtures/case-4-first-release-archive-review/expected.json
 create mode 100644 tools/skill-evals/evals/release-prepare/step-2-prep/fixtures/case-4-first-release-archive-review/report.md
 create mode 100644 tools/skill-evals/evals/release-promote/step-2-emit-commands/fixtures/case-5-convenience-artefacts/expected.json
 create mode 100644 tools/skill-evals/evals/release-promote/step-2-emit-commands/fixtures/case-5-convenience-artefacts/report.md
 create mode 100644 tools/skill-evals/evals/release-rc-cut/step-0-preflight/fixtures/case-4-archive-unreviewed/expected.json
 create mode 100644 tools/skill-evals/evals/release-rc-cut/step-0-preflight/fixtures/case-4-archive-unreviewed/report.md
 copy tools/skill-evals/evals/release-rc-cut/step-2-tag-build-sign/fixtures/{case-1-svnpubsub-sha512 => case-4-git-archive-reproducible}/expected.json (82%)
 create mode 100644 tools/skill-evals/evals/release-rc-cut/step-2-tag-build-sign/fixtures/case-4-git-archive-reproducible/report.md
 create mode 100644 tools/skill-evals/evals/release-rc-cut/step-2b-reproducibility/fixtures/assertions.json
 create mode 100644 tools/skill-evals/evals/release-rc-cut/step-2b-reproducibility/fixtures/case-1-source-only/expected.json
 create mode 100644 tools/skill-evals/evals/release-rc-cut/step-2b-reproducibility/fixtures/case-1-source-only/report.md
 create mode 100644 tools/skill-evals/evals/release-rc-cut/step-2b-reproducibility/fixtures/case-2-source-and-binaries-ci-signed/expected.json
 create mode 100644 tools/skill-evals/evals/release-rc-cut/step-2b-reproducibility/fixtures/case-2-source-and-binaries-ci-signed/report.md
 create mode 100644 tools/skill-evals/evals/release-rc-cut/step-2b-reproducibility/fixtures/case-3-checks-off/expected.json
 create mode 100644 tools/skill-evals/evals/release-rc-cut/step-2b-reproducibility/fixtures/case-3-checks-off/report.md
 create mode 100644 tools/skill-evals/evals/release-rc-cut/step-2b-reproducibility/fixtures/output-spec.md
 create mode 100644 tools/skill-evals/evals/release-rc-cut/step-2b-reproducibility/fixtures/step-config.json
 create mode 100644 tools/skill-evals/evals/release-verify-rc/step-9-reproducibility/fixtures/case-1-identical-pass/expected.json
 create mode 100644 tools/skill-evals/evals/release-verify-rc/step-9-reproducibility/fixtures/case-1-identical-pass/report.md
 create mode 100644 tools/skill-evals/evals/release-verify-rc/step-9-reproducibility/fixtures/case-2-differs-fail/expected.json
 create mode 100644 tools/skill-evals/evals/release-verify-rc/step-9-reproducibility/fixtures/case-2-differs-fail/report.md
 create mode 100644 tools/skill-evals/evals/release-verify-rc/step-9-reproducibility/fixtures/case-3-content-identical-warn/expected.json
 create mode 100644 tools/skill-evals/evals/release-verify-rc/step-9-reproducibility/fixtures/case-3-content-identical-warn/report.md
 create mode 100644 tools/skill-evals/evals/release-verify-rc/step-9-reproducibility/fixtures/case-4-content-identical-ci-signed-fail/expected.json
 create mode 100644 tools/skill-evals/evals/release-verify-rc/step-9-reproducibility/fixtures/case-4-content-identical-ci-signed-fail/report.md
 create mode 100644 tools/skill-evals/evals/release-verify-rc/step-9-reproducibility/fixtures/case-5-convenience-artefact-differs/expected.json
 create mode 100644 tools/skill-evals/evals/release-verify-rc/step-9-reproducibility/fixtures/case-5-convenience-artefact-differs/report.md
 copy tools/skill-evals/evals/release-verify-rc/{step-2-verify-signatures => step-9-reproducibility}/fixtures/grading-schema.json (100%)
 create mode 100644 tools/skill-evals/evals/release-verify-rc/step-9-reproducibility/fixtures/output-spec.md
 create mode 100644 tools/skill-evals/evals/release-verify-rc/step-9-reproducibility/fixtures/step-config.json
 create mode 100644 tools/skill-evals/evals/release-vote-draft/step-2-vote-draft/fixtures/assertions.json
 copy tools/skill-evals/evals/setup-isolated-setup-doctor/interpret-probes/fixtures/{case-1-all-pass => case-10-gateway-pass}/expected.json (100%)
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-doctor/interpret-probes/fixtures/case-10-gateway-pass/report.md
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-doctor/interpret-probes/fixtures/case-11-gateway-not-running/expected.json
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-doctor/interpret-probes/fixtures/case-11-gateway-not-running/report.md
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-doctor/interpret-probes/fixtures/case-12-gateway-socket-denied/expected.json
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-doctor/interpret-probes/fixtures/case-12-gateway-socket-denied/report.md
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-doctor/interpret-probes/fixtures/case-13-gateway-no-podman-backend/expected.json
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-doctor/interpret-probes/fixtures/case-13-gateway-no-podman-backend/report.md
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-doctor/interpret-probes/fixtures/case-14-scratch-shared-session-root/expected.json
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-doctor/interpret-probes/fixtures/case-14-scratch-shared-session-root/report.md
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-doctor/interpret-probes/fixtures/case-15-gateway-relative-container-host/expected.json
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-doctor/interpret-probes/fixtures/case-15-gateway-relative-container-host/report.md
 copy tools/skill-evals/evals/{ci-runner-audit/step-reporting/fixtures/case-2-no-security-overclaim => setup-isolated-setup-install/step-hardware-key/fixtures/case-1-no-key}/case-meta.json (100%)
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-install/step-hardware-key/fixtures/case-1-no-key/expected.json
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-install/step-hardware-key/fixtures/case-1-no-key/report.md
 copy tools/skill-evals/evals/{ci-runner-audit/step-reporting/fixtures/case-2-no-security-overclaim => setup-isolated-setup-install/step-hardware-key/fixtures/case-2-slots-off}/case-meta.json (100%)
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-install/step-hardware-key/fixtures/case-2-slots-off/expected.json
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-install/step-hardware-key/fixtures/case-2-slots-off/report.md
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-install/step-hardware-key/fixtures/case-3-injection/expected.json
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-install/step-hardware-key/fixtures/case-3-injection/report.md
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-install/step-hardware-key/fixtures/output-spec.md
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-install/step-hardware-key/fixtures/step-config.json
 create mode 100644 tools/skill-evals/evals/setup-isolated-setup-install/step-hardware-key/fixtures/user-prompt-template.md
 create mode 100644 tools/skill-evals/evals/setup/preflight-floor/fixtures/case-8-unknown-plugin-list/expected.json
 create mode 100644 tools/skill-evals/evals/setup/preflight-floor/fixtures/case-8-unknown-plugin-list/report.md
 create mode 100644 tools/skill-evals/evals/setup/step-adopt-stamp/fixtures/case-1-migrate-and-scope/expected.json
 create mode 100644 tools/skill-evals/evals/setup/step-adopt-stamp/fixtures/case-1-migrate-and-scope/report.md
 create mode 100644 tools/skill-evals/evals/setup/step-adopt-stamp/fixtures/output-spec.md
 create mode 100644 tools/skill-evals/evals/setup/step-adopt-stamp/fixtures/step-config.json
 create mode 100644 tools/skill-evals/evals/setup/step-adopt-stamp/fixtures/user-prompt-template.md
 create mode 100644 tools/skill-evals/evals/setup/step-config-stamp/fixtures/case-1-adopted-project/expected.json
 create mode 100644 tools/skill-evals/evals/setup/step-config-stamp/fixtures/case-1-adopted-project/report.md
 create mode 100644 tools/skill-evals/evals/setup/step-config-stamp/fixtures/case-2-unadopted-project/expected.json
 create mode 100644 tools/skill-evals/evals/setup/step-config-stamp/fixtures/case-2-unadopted-project/report.md
 create mode 100644 tools/skill-evals/evals/setup/step-config-stamp/fixtures/case-3-nothing-configured-yet/expected.json
 create mode 100644 tools/skill-evals/evals/setup/step-config-stamp/fixtures/case-3-nothing-configured-yet/report.md
 create mode 100644 tools/skill-evals/evals/setup/step-config-stamp/fixtures/case-4-adopted-untouched-skill/expected.json
 create mode 100644 tools/skill-evals/evals/setup/step-config-stamp/fixtures/case-4-adopted-untouched-skill/report.md
 create mode 100644 tools/skill-evals/evals/setup/step-config-stamp/fixtures/output-spec.md
 create mode 100644 tools/skill-evals/evals/setup/step-config-stamp/fixtures/step-config.json
 create mode 100644 tools/skill-evals/evals/setup/step-config-stamp/fixtures/user-prompt-template.md
 create mode 100644 tools/skill-evals/evals/setup/step-reconcile/fixtures/case-1-clean-sweep/expected.json
 create mode 100644 tools/skill-evals/evals/setup/step-reconcile/fixtures/case-1-clean-sweep/report.md
 create mode 100644 tools/skill-evals/evals/setup/step-reconcile/fixtures/case-2-stale-anchor/expected.json
 create mode 100644 tools/skill-evals/evals/setup/step-reconcile/fixtures/case-2-stale-anchor/report.md
 create mode 100644 tools/skill-evals/evals/setup/step-reconcile/fixtures/case-3-sandboxed-run/expected.json
 create mode 100644 tools/skill-evals/evals/setup/step-reconcile/fixtures/case-3-sandboxed-run/report.md
 create mode 100644 tools/skill-evals/evals/setup/step-reconcile/fixtures/grading-schema.json
 create mode 100644 tools/skill-evals/evals/setup/step-reconcile/fixtures/output-spec.md
 create mode 100644 tools/skill-evals/evals/setup/step-reconcile/fixtures/step-config.json
 create mode 100644 tools/skill-evals/evals/setup/step-reconcile/fixtures/user-prompt-template.md
 create mode 100644 tools/skill-evals/evals/setup/step-upgrade-stamp/fixtures/case-1-mixed-checks/expected.json
 create mode 100644 tools/skill-evals/evals/setup/step-upgrade-stamp/fixtures/case-1-mixed-checks/report.md
 create mode 100644 tools/skill-evals/evals/setup/step-upgrade-stamp/fixtures/grading-schema.json
 create mode 100644 tools/skill-evals/evals/setup/step-upgrade-stamp/fixtures/output-spec.md
 create mode 100644 tools/skill-evals/evals/setup/step-upgrade-stamp/fixtures/step-config.json
 create mode 100644 tools/skill-evals/evals/setup/step-upgrade-stamp/fixtures/user-prompt-template.md
 create mode 100644 tools/skill-evals/evals/setup/step-verify/fixtures/case-1-dev-to-dev-delta/expected.json
 create mode 100644 tools/skill-evals/evals/setup/step-verify/fixtures/case-1-dev-to-dev-delta/report.md
 create mode 100644 tools/skill-evals/evals/setup/step-verify/fixtures/case-2-unreadable-clone/expected.json
 create mode 100644 tools/skill-evals/evals/setup/step-verify/fixtures/case-2-unreadable-clone/report.md
 create mode 100644 tools/skill-evals/evals/setup/step-verify/fixtures/output-spec.md
 create mode 100644 tools/skill-evals/evals/setup/step-verify/fixtures/step-config.json
 create mode 100644 tools/skill-evals/evals/setup/step-verify/fixtures/user-prompt-template.md
 create mode 100755 tools/skill-evals/magpie-run-evals.sh
 create mode 100644 tools/skill-evals/tests/test_run_evals_wrapper.py
 create mode 100644 tools/spec-loop/specs/container-gateway.md
 create mode 100644 tools/spec-loop/specs/copilot-runtime.md